Home      Library      Discussions      About
Join us

@nict.go.jp

Aug 26, 2018
Computation and Language

Exploring Recombination for Efficient Decoding of Neural Machine Tr…

In Neural Machine Translation (NMT), the decoder can capture the features of the entire prediction history with neural connections and representation…
Aug 27, 2018
Computer Vision

Exploring the Applications of Faster R-CNN and Single-Shot Multi-box …

The ultimate goal of a baby detection task concerns detecting the presence of a baby and other objects in a sequence of 2D images, tracking them and …
Jun 11, 2018
Robotics
Computation and Language

A Multimodal Classifier Generative Adversarial Network for Carry and …

This paper focuses on a multimodal language understanding method for carry-and-place tasks with domestic service robots. We address the case of ambig…
May 01, 2018
Computation and Language

Dynamic Sentence Sampling for Efficient Training of Neural Machine …

Traditional Neural machine translation (NMT) involves a fixed training procedure where each sentence is sampled once during each epoch. In reality, s…
Aug 15, 2017
Information Theory

Throughput Enhancement of Multicarrier Cognitive M2M Networks: Univ…

We consider a cognitive radio network consisting of a primary cellular system and a secondary cognitive machine-to-machine (M2M) system, and study th…
Apr 30, 2019
Machine Learning
Sound
Audio and Speech Processing

Incorporating Symbolic Sequential Modeling for Speech Enhancement

In a noisy environment, a lossy speech signal can be automatically restored by a listener if he/she knows the language well. That is, with the built-…
Nov 14, 2013

Pulsed Sagnac polarization-entangled photon source with a PPKTP cryst…

We demonstrate pulsed polarization-entangled photons generated from a periodically poled $\mathrm{KTiOPO_4}$ (PPKTP) crystal in a Sagnac interferomet…
Dec 26, 2014

Particle Acceleration In Plasmoid Ejections Derived From Radio Drifti…

We report observations of slowly drifting pulsating structures (DPS) in the 0.8-4.5 GHz frequency range of the RT4 and RT5 radio spectrographs at Ond…
Jul 13, 2018

Fast Amplification and Rephasing of Entangled Cat States in a Qubit…

We study a qubit-oscillator system, with a time-dependent coupling coefficient, and present a scheme for generating entangled Schr\"odinger-cat state…
Jun 01, 2018
Computation and Language
Artificial Intelligence
Machine Learning

A Survey of Domain Adaptation for Neural Machine Translation

Neural machine translation (NMT) is a deep learning based approach for machine translation, which yields the state-of-the-art translation performance…
Jul 14, 2018
Computation and Language

Recurrent Stacking of Layers for Compact Neural Machine Translation …

In Neural Machine Translation (NMT), the most common practice is to stack a number of recurrent or feed-forward layers in the encoder and the decoder…
Jun 17, 2019
Robotics

Understanding Natural Language Instructions for Fetching Daily Object…

In this paper, we address multimodal language understanding for unconstrained fetching instruction in domestic service robots context. A typical fetc…
Nov 16, 2019
Machine Learning
Materials Science

In this study, we extended the deep learning–based reading periodic table method, which reads the periodic table and learns the laws of elements. We solved two problems. First, we determined whether we can use the deep learning method of reading per…

Deep-Learning Estimation of Band Gap with the Reading-Periodic-Table …

We verified that the deep learning method named reading periodic table introduced by ref. Deep Learning Model for Finding New Superconductors, which …
Sep 19, 2018
Computation and Language

In this paper, we investigated the noisy data problem in NMT. We designed a classification system to filter the noisy data for the WMT18 shared parallel corpus filtering task and built NMT systems using the selected data.

NICT's Corpus Filtering Systems for the WMT18 Parallel Corpus Filteri…

This paper presents the NICT's participation in the WMT18 shared parallel corpus filtering task. The organizers provided 1 billion words German-Engli…
Mar 25, 2013
Optics

Widely tunable single photon source with high purity at telecom wav…

We theoretically and experimentally investigate the spectral tunability and purity of photon pairs generated from spontaneous parametric down convers…
Nov 06, 2016

Solar Flare Prediction Model with Three Machine-Learning Algorithms …

We developed a flare prediction model using machine learning, which is optimized to predict the maximum class of flares occurring in the following 24…
Dec 03, 2018
Machine Learning
Computation and Language

Deep Learning Model for Finding New Superconductors

Superconductivity has been extensively studied since its discovery in 1911. However, the feasibility of room-temperature superconductivity is unknown…
Jan 14, 2010
Information Theory

PPM demodulation: On approaching fundamental limits of optical comm…

We consider the problem of demodulating M-ary optical PPM (pulse-position modulation) waveforms, and propose a structured receiver whose mean probabi…
Jun 19, 2019
Computation and Language

Multilingual Multi-Domain Adaptation Approaches for Neural Machine …

In this paper, we propose two novel methods for domain adaptation for the attention-only neural machine translation (NMT) model, i.e., the Transforme…
Oct 30, 2018
Computation and Language

Unsupervised Neural Machine Translation Initialized by Unsupervised …

Recent work achieved remarkable results in training neural machine translation (NMT) systems in a fully unsupervised way, with new and dedicated arch…
There aren't more papers

Request Comment

or Invite via email
You are asking your first question!
How to quickly get a good answer:
  • Keep your question short and to the point
  • Check for grammar or spelling errors.
  • Phrase it like a question
Test
Test description